parallel-execution

Use when multiple subtasks have no shared files or dependencies and can be executed simultaneously.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code/skills/parallel-execution/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands and a clearly sequenced, validated workflow including error-recovery guidance. Its main weaknesses are some redundancy inflating length and a monolithic single-file structure with no progressive disclosure of detail into separate references.

Suggestions

Remove redundancy: the 'Remember' bullet list and final 'Key Pattern' line largely restate earlier content — collapse them into the existing sections to tighten the token budget.

Consider moving the large 'Example: Converting Multiple Files' block and/or 'Error Handling' into a separate referenced file (e.g., EXAMPLES.md) with a one-line pointer, to achieve one-level-deep progressive disclosure.

Keep the lean core (process steps + commands) inline and push the extended examples out so the overview stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no padding about what parallelism is), but the ~165-line length includes redundancy — the 'Remember' section and closing 'Key Pattern' line restate points already made — so it could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands ('bash .opencode/skills/task-management/router.sh parallel {feature}') and complete task() call examples with real arguments, matching 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	The 5-step process is clearly sequenced with an explicit validation checkpoint (Step 4 status check) and a feedback/error-recovery section, and it correctly waits for all batch tasks before proceeding, matching 'clear sequence with explicit validation steps'.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a single ~165-line monolithic file with no bundle files or one-level-deep references; content like the long conversion example and error handling is inline that could be split out, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description provides a clear, explicit trigger condition but is framed as a 'when' clause rather than a statement of concrete actions, leaving the 'what' only implied. It is concise and avoids fluff but lacks the breadth of natural trigger terms and concrete capability listing needed for the top level.

Suggestions

Lead with a concrete action statement (e.g., 'Executes multiple independent subtasks simultaneously in a single message') before the 'Use when' clause so the 'what' is explicit, not implied.

Add common trigger variations users would say, such as 'parallel', 'at the same time', or 'simultaneously', to broaden natural keyword coverage.

Tighten distinctiveness by naming the specific mechanism (e.g., 'via multiple task() calls in one message') so it is less likely to collide with generic task-management skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('multiple subtasks ... no shared files or dependencies ... executed simultaneously') but states a trigger condition rather than listing concrete actions the skill performs, matching 'Names domain and some actions, but not comprehensive' rather than the multi-action level-3 anchor.	2 / 3
Completeness	It has an explicit 'Use when ...' clause answering 'when' clearly, but the 'what does this do' half is only implied from the condition, so only one of the two required answers is explicit (capping it at 2).	2 / 3
Trigger Term Quality	It includes natural phrases like 'multiple subtasks', 'no shared files or dependencies', and 'simultaneously', but omits the very common variation 'parallel' as an explicit trigger term, so coverage is partial rather than the broad level-3 set.	2 / 3
Distinctiveness Conflict Risk	The niche (independent parallelizable subtasks) is reasonably specific, but the condition-based phrasing could still overlap with general task-management or task-breakdown skills, fitting 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: darrenhinde/OpenAgentsControl
Path: plugins/claude-code/skills/parallel-execution/SKILL.md
Commit: 37ca233

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.